A cognitive system for business and technical support: A case study

Dhoolia, Pankaj; Chugh, P.; Costa, Paolo; Gantayat, Neelamadhav; Gupta, Monika; Kambhatla, Nanda; Kumar, Rajesh; Mani, Senthil; Mitra, Prasenjit; Rogerson, C.; Saxena, Mayur

doi:10.1147/jrd.2016.2631398

Cited by 9 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More specifically, the predictive model was built with the IBM SPSS Modeler Flow tool, provided by the IBM Watson Studio, utilizing the XGBoost linear regression algorithm, which is part of the available models section. It is worth mentioning that the XGBoost model in the IBM Watson Studio carries out the automatic encoding of the categorical variables [15]. After the completion of the feature engineering processes described in the previous section, we used the extracted features (Table II) to feed the XGBoost regression algorithm (Fig.…”

Section: B Deployment To the Cloudmentioning

confidence: 99%

“…4). Eventually, the process comes up with the creation of a continuously available model, as a service, acting like a secure API (Application Programming Interface) endpoint, under the HTTPS (Hypertext Transfer Protocol Secure) protocol [15]. This API accepts requests in JSON (JavaScript Object Notation) format that must contain the exact features that used to train the model, and returns a float value that represents the predicted CTR in decimal format.…”

Section: B Deployment To the Cloudmentioning

confidence: 99%

See 1 more Smart Citation

Building a Cloud-based Regression Model to Predict Click-through Rate in Business Messaging Campaigns

Deligiannis¹,

Argyriou²,

Kourtesis³

2020

IJMO

View full text Add to dashboard Cite

The goal of the research presented here is to describe an innovative approach to predicting the impact of a business messaging campaign, by estimating the percentage of message recipients who will engage with a message. The motivation is to facilitate business marketers to address the problem of estimating the return on investment coming from a potential messaging campaign. The presented solution relies on the processing of large scale business data, taking into account state-of-the-art predictive algorithms, GDPR compliance requirements, and the challenge of increased data security and availability. In this paper we discuss the design of the core functional components of a system that could make this possible, which encompasses predictive analytics, data mining and machine learning technologies in a cloud computing environment.

show abstract

Section: B Deployment To the Cloudmentioning

confidence: 99%

Section: B Deployment To the Cloudmentioning

confidence: 99%

Building a Cloud-based Regression Model to Predict Click-through Rate in Business Messaging Campaigns

Deligiannis¹,

Argyriou²,

Kourtesis³

2020

IJMO

View full text Add to dashboard Cite

show abstract

“…Technically, the described estimation algorithm is being implemented as a scheduled Python Jupyter Notebook with an Apache Spark configuration (i.e., cluster of computers), storing the extracted values in a cloud-based database utilizing the IBM cloud infrastructure [46,47,48]. Figure 5 depicts an overall view of the way that the described components interact with each other during the algorithm's deployment to the cloud.…”

Section: B Algorithm Design and Deploymentmentioning

confidence: 99%

Designing a Real-Time Data-Driven Customer Churn Risk Indicator for Subscription Commerce

Deligiannis¹,

Argyriou²

2020

IJIEEB

View full text Add to dashboard Cite

One of the main goals of customer relationship management is to reduce or eliminate "customer churn", i.e. loss of existing customers. This paper introduces a prototype algorithm to estimate a continuously updated indicator of the probability of an existing customer to cease purchasing from a subscription commerce business. The investigation is focused on the case of repeat consumers of subscription commerce products which require regular replacement or replenishment. The motivation is to help marketers to make targeted proactive retention actions by categorizing regular customers into groups of similar estimated churn risk. The proposed algorithm re-computes the probability of churn for each customer at regular intervals using past purchase transaction data and incorporating subscription-based business logic. We describe the detailed process from data collection and feature engineering to the algorithm's design. We also present evaluation results of the algorithm's performance based on a pilot test that took place on a consumables ecommerce business. The results suggest a significant capability of the proposed algorithm in capturing the purchasing intentions of repeat customers, regardless of the risk group they belong to.

show abstract

“…Research on DVA mainly focuses on the development of AI and natural language with limited discussion on the improvement of enterprise operations (e.g. Ghosh and Pherwani, 2015; Dhoolia et al , 2017; Lee et al , 2017). Han and Yang (2018) carried out a survey to understand what motivates users’ satisfaction in using DVA.…”

Section: Introductionmentioning

confidence: 99%

Exploring the opportunity of digital voice assistants in the logistics and transportation industry

Hsiao

Chang

2019

JEIM

View full text Add to dashboard Cite

Purpose The logistics industry has benefited hugely from the growth of e-commerce. The logistics and transportation industry operators have realized that higher-quality service and logistics management provides the competitive edge as the primary channel of communication with consumers. Digital voice assistants (DVA) is an information system based on an artificial intelligence framework that can interact through voice, such that a deliveryman can query for or use information in a relatively short time. The purpose of this paper is to explore the value of DVA in logistic service. Design/methodology/approach This study aims to develop a framework for innovation and logistics service capabilities of logistics and transportation services to structure a model based on the analysis hierarchy process method to discuss the factors considered when adopting DVA. Findings The results of this study implied that common problem and expectations of current operators in the delivery of goods and their expectations of DVA. Practical implications Innovative operations and planning are possible with information technology-enabled logistic services. It is important to identify relevant DVA development avenues. Originality/value The purpose of this study is to show which factors are significant to the logistics and transportation industry using DVA to aid the deliverymen, and it provides guidance for manager evaluating adopted DVA and its object.

show abstract

A cognitive system for business and technical support: A case study

Cited by 9 publications

References 8 publications

Building a Cloud-based Regression Model to Predict Click-through Rate in Business Messaging Campaigns

Building a Cloud-based Regression Model to Predict Click-through Rate in Business Messaging Campaigns

Designing a Real-Time Data-Driven Customer Churn Risk Indicator for Subscription Commerce

Exploring the opportunity of digital voice assistants in the logistics and transportation industry

Contact Info

Product

Resources

About